Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2283 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1494. Min Range: -6.1494
Max Act: 6.1494. Min Act: -0.1700
Data Index: 7852565 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1494. Min Range: -6.1494
Max Act: 6.1182. Min Act: -0.1700
Data Index: 5081362 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1494. Min Range: -6.1494
Max Act: 6.0869. Min Act: -0.1700
Data Index: 6928686 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1494. Min Range: -6.1494
Max Act: 6.0557. Min Act: -0.1700
Data Index: 1223604 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1494. Min Range: -6.1494
Max Act: 6.0244. Min Act: -0.1700
Data Index: 7107131 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1494. Min Range: -6.1494
Max Act: 6.0244. Min Act: -0.1700
Data Index: 2932942 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1494. Min Range: -6.1494
Max Act: 5.9932. Min Act: -0.1700
Data Index: 5316318 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1494. Min Range: -6.1494
Max Act: 5.9932. Min Act: -0.1700
Data Index: 2808214 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1494. Min Range: -6.1494
Max Act: 5.9932. Min Act: -0.1700
Data Index: 1065975 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1494. Min Range: -6.1494
Max Act: 5.9932. Min Act: -0.1700
Data Index: 887483 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1494. Min Range: -6.1494
Max Act: 5.9932. Min Act: -0.1700
Data Index: 6879710 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1494. Min Range: -6.1494
Max Act: 5.9932. Min Act: -0.1700
Data Index: 2773752 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1494. Min Range: -6.1494
Max Act: 5.9619. Min Act: -0.1700
Data Index: 5604355 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1494. Min Range: -6.1494
Max Act: 5.9307. Min Act: -0.1700
Data Index: 5416826 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1494. Min Range: -6.1494
Max Act: 5.8994. Min Act: -0.1700
Data Index: 2993502 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1494. Min Range: -6.1494
Max Act: 5.8994. Min Act: -0.1700
Data Index: 6944271 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1494. Min Range: -6.1494
Max Act: 5.8994. Min Act: -0.1700
Data Index: 5648524 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1494. Min Range: -6.1494
Max Act: 5.8369. Min Act: -0.1700
Data Index: 3312024 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1494. Min Range: -6.1494
Max Act: 5.8369. Min Act: -0.1700
Data Index: 1598040 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1494. Min Range: -6.1494
Max Act: 5.8682. Min Act: -0.1700
Data Index: 3859236 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #19